nerdd-module 0.3.24__tar.gz → 0.3.26__tar.gz

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: nerdd-module
-Version: 0.3.24
+Version: 0.3.26
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/converters/converter.py

@@ -38,17 +38,17 @@ class Converter(ABC):
     @classmethod
     def __init_subclass__(
         cls,
-        is_abstract: bool = False,
         **kwargs: Any,
     ) -> None:
         super().__init_subclass__(**kwargs)
 
-        if hasattr(cls, "config"):
-            data_types = cls.config["data_types"]
-            output_formats = cls.config["output_formats"]
-        else:
-            data_types = None
-            output_formats = None
+        assert hasattr(
+            cls, "config"
+        ), "All subclasses of Converter need to have a config attribute of type ConverterConfig"
+
+        data_types = cls.config["data_types"]
+        output_formats = cls.config["output_formats"]
+        is_abstract = cls.config.get("is_abstract", False)
 
         if not is_abstract:
             if isinstance(data_types, str) or data_types is ALL:

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/converters/converter_config.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Union
+from typing import List, Union
 
 from ..polyfills import Literal, TypedDict
 
@@ -10,6 +10,7 @@ ALL_TYPE = Literal["ALL"]
 ALL: ALL_TYPE = "ALL"
 
 
-class ConverterConfig(TypedDict):
-    data_types: Optional[Union[str, List[str], ALL_TYPE]]
-    output_formats: Optional[Union[str, List[str], ALL_TYPE]]
+class ConverterConfig(TypedDict, total=False):
+    data_types: Union[str, List[str], ALL_TYPE]
+    output_formats: Union[str, List[str], ALL_TYPE]
+    is_abstract: bool

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/model/__init__.py

@@ -1,4 +1,3 @@
-from .assign_mol_id_step import *
 from .assign_name_step import *
 from .convert_representations_step import *
 from .model import *

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/model/read_input_step.py

@@ -13,8 +13,9 @@ class ReadInputStep(Step):
         self._input = input
 
     def _run(self, source: Iterator[dict]) -> Iterator[dict]:
-        for entry in self._explorer.explore(self._input):
+        for mol_id, entry in enumerate(self._explorer.explore(self._input)):
             record = dict(
+                mol_id=mol_id,
                 input_text=entry.raw_input,
                 source=entry.source,
                 input_type=entry.input_type,

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/model/simple_model.py

@@ -18,7 +18,6 @@ from ..preprocessing import PreprocessingStep
 from ..problem import Problem
 from ..steps import Step
 from ..util import get_file_path_to_instance
-from .assign_mol_id_step import AssignMolIdStep
 from .assign_name_step import AssignNameStep
 from .convert_representations_step import ConvertRepresentationsStep
 from .enforce_schema_step import EnforceSchemaStep
@@ -52,11 +51,10 @@ class SimpleModel(Model):
         self, input: Any, input_format: Optional[str], **kwargs: Any
     ) -> List[Step]:
         return [
-            AssignMolIdStep(),
             AssignNameStep(),
             *self._preprocessing_steps,
             # the following step ensures that the column preprocessed_mol is created
-            # (even is self._preprocessing_steps is empty)
+            # (even if self._preprocessing_steps is empty)
             CustomPreprocessingStep(self),
         ]
 
@@ -214,4 +212,7 @@ class CustomPreprocessingStep(PreprocessingStep):
         self.model = model
 
     def _preprocess(self, mol: Mol) -> Tuple[Optional[Mol], List[Problem]]:
-        return self.model._preprocess(mol)
+        try:
+            return self.model._preprocess(mol)
+        except Exception as e:
+            return None, [Problem(type="preprocessing_error", message=str(e))]

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/__init__.py

@@ -5,3 +5,4 @@ from .pandas_writer import *
 from .record_list_writer import *
 from .sdf_writer import *
 from .writer import *
+from .writer_config import *

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/csv_writer.py

@@ -3,11 +3,12 @@ from itertools import chain
 from typing import IO, Any, Dict, Iterable
 
 from .file_writer import FileLike, FileWriter
+from .writer_config import WriterConfig
 
 __all__ = ["CsvWriter"]
 
 
-class CsvWriter(FileWriter, output_format="csv"):
+class CsvWriter(FileWriter):
     def __init__(self, output_file: FileLike) -> None:
         super().__init__(output_file, writes_bytes=False)
 
@@ -22,3 +23,5 @@ class CsvWriter(FileWriter, output_format="csv"):
         writer.writeheader()
         for entry in chain([first_entry], entry_iter):
             writer.writerow(entry)
+
+    config = WriterConfig(output_format="csv")

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/file_writer.py

@@ -4,6 +4,7 @@ from pathlib import Path
 from typing import IO, Any, BinaryIO, Iterable, TextIO, Union
 
 from .writer import Writer
+from .writer_config import WriterConfig
 
 StreamWriter = codecs.getwriter("utf-8")
 
@@ -13,7 +14,7 @@ __all__ = ["FileWriter", "FileLike"]
 FileLike = Union[str, Path, TextIO, BinaryIO]
 
 
-class FileWriter(Writer, is_abstract=True):
+class FileWriter(Writer):
     """Abstract class for writers."""
 
     def __init__(self, output_file: FileLike, writes_bytes: bool = False) -> None:
@@ -39,3 +40,5 @@ class FileWriter(Writer, is_abstract=True):
     def writes_bytes(self) -> bool:
         """Whether the writer writes bytes."""
         return self._writes_bytes
+
+    config = WriterConfig(is_abstract=True, output_format="file")

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/iterator_writer.py

@@ -1,13 +1,16 @@
 from typing import Iterable
 
 from .writer import Writer
+from .writer_config import WriterConfig
 
 __all__ = ["IteratorWriter"]
 
 
-class IteratorWriter(Writer, output_format="iterator"):
+class IteratorWriter(Writer):
     def __init__(self) -> None:
         pass
 
     def write(self, records: Iterable[dict]) -> Iterable[dict]:
         return records
+
+    config = WriterConfig(output_format="iterator")

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/pandas_writer.py

@@ -3,14 +3,17 @@ from typing import Iterable
 import pandas as pd
 
 from .writer import Writer
+from .writer_config import WriterConfig
 
 __all__ = ["PandasWriter"]
 
 
-class PandasWriter(Writer, output_format="pandas"):
+class PandasWriter(Writer):
     def __init__(self) -> None:
         pass
 
     def write(self, records: Iterable[dict]) -> pd.DataFrame:
         df = pd.DataFrame(records)
         return df
+
+    config = WriterConfig(output_format="pandas")

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/record_list_writer.py

@@ -1,13 +1,16 @@
 from typing import Iterable, List
 
 from .writer import Writer
+from .writer_config import WriterConfig
 
 __all__ = ["RecordListWriter"]
 
 
-class RecordListWriter(Writer, output_format="record_list"):
+class RecordListWriter(Writer):
     def __init__(self) -> None:
         pass
 
     def write(self, records: Iterable[dict]) -> List[dict]:
         return list(records)
+
+    config = WriterConfig(output_format="record_list")

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/sdf_writer.py

@@ -3,11 +3,12 @@ from typing import IO, Any, Dict, Iterable
 from rdkit.Chem import Mol, SDWriter
 
 from .file_writer import FileLike, FileWriter
+from .writer_config import WriterConfig
 
 __all__ = ["SdfWriter"]
 
 
-class SdfWriter(FileWriter, output_format="sdf"):
+class SdfWriter(FileWriter):
     def __init__(self, output_file: FileLike) -> None:
         super().__init__(output_file, writes_bytes=False)
 
@@ -40,3 +41,5 @@ class SdfWriter(FileWriter, output_format="sdf"):
                 writer.write(mol)
         finally:
             writer.close()
+
+    config = WriterConfig(output_format="sdf")

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module/output/writer.py

@@ -3,7 +3,7 @@ from __future__ import annotations
 import codecs
 from abc import ABC, abstractmethod
 from functools import partial
-from typing import Any, Dict, Iterable, List, Optional
+from typing import Any, Dict, Iterable, List
 
 from typing_extensions import Protocol
 
@@ -27,11 +27,16 @@ class Writer(ABC):
     @classmethod
     def __init_subclass__(
         cls,
-        output_format: Optional[str] = None,
-        is_abstract: bool = False,
         **kwargs: Any,
     ) -> None:
         super().__init_subclass__(**kwargs)
+
+        assert hasattr(
+            cls, "config"
+        ), "All subclasses of Writer need to have a config attribute of type WriterConfig"
+        output_format = cls.config["output_format"]
+        is_abstract = cls.config.get("is_abstract", False)
+
         if not is_abstract:
             assert output_format is not None, "output_format must not be None"
             _factories[output_format] = partial(call_with_mappings, cls)

nerdd_module-0.3.26/nerdd_module/output/writer_config.py

@@ -0,0 +1,8 @@
+from ..polyfills import TypedDict
+
+__all__ = ["WriterConfig"]
+
+
+class WriterConfig(TypedDict, total=False):
+    output_format: str
+    is_abstract: bool

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: nerdd-module
-Version: 0.3.24
+Version: 0.3.26
 Summary: Base package to create NERDD modules
 Author-email: Steffen Hirte <steffen.hirte@univie.ac.at>
 Maintainer-email: Steffen Hirte <steffen.hirte@univie.ac.at>

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/nerdd_module.egg-info/SOURCES.txt

@@ -45,7 +45,6 @@ nerdd_module/input/string_reader.py
 nerdd_module/input/tar_reader.py
 nerdd_module/input/zip_reader.py
 nerdd_module/model/__init__.py
-nerdd_module/model/assign_mol_id_step.py
 nerdd_module/model/assign_name_step.py
 nerdd_module/model/convert_representations_step.py
 nerdd_module/model/enforce_schema_step.py
@@ -61,6 +60,7 @@ nerdd_module/output/pandas_writer.py
 nerdd_module/output/record_list_writer.py
 nerdd_module/output/sdf_writer.py
 nerdd_module/output/writer.py
+nerdd_module/output/writer_config.py
 nerdd_module/polyfills/__init__.py
 nerdd_module/polyfills/block_logs.py
 nerdd_module/polyfills/files.py

{nerdd_module-0.3.24 → nerdd_module-0.3.26}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "nerdd-module"
-version = "0.3.24"
+version = "0.3.26"
 description = "Base package to create NERDD modules"
 readme = "README.md"
 license = { file = "LICENSE" }

nerdd_module-0.3.24/nerdd_module/model/assign_mol_id_step.py

@@ -1,17 +0,0 @@
-from typing import Iterator
-
-from ..steps import Step
-
-__all__ = ["AssignMolIdStep"]
-
-
-class AssignMolIdStep(Step):
-    def __init__(self) -> None:
-        super().__init__()
-
-    def _run(self, source: Iterator[dict]) -> Iterator[dict]:
-        mol_id = 0
-        for record in source:
-            record["mol_id"] = mol_id
-            mol_id += 1
-            yield record